Gender Bias Evaluation on RealWorldQuestioning Investment Recommendations
0.9Shannon Entropy (T-test Statistic)ChatGPT-4-turbo
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| ChatGPT-4-turboIteration=1, Evaluation Protocol=Female vs Male T-test2025.05 | 0.9 | 0.36 | 0.87 | 0.38 | -0.68 | 0.49 | |
| ChatGPT-3.5-turboIteration=1, Evaluation Protocol=Female vs Male T-test2025.05 | 0.27 | 0.78 | -0.18 | 0.85 | 0.57 | 0.56 | |
| DeepSeek-R1Iteration=1, Evaluation Protocol=Female vs Male T-test2025.05 | -0.28 | 0.77 | 1 | 0.31 | -1.29 | 0.19 | |
| Llama-3Iteration=1, Evaluation Protocol=Female vs Male T-test2025.05 | -0.3 | 0.76 | 1.69 | 0.09 | -0.44 | 0.65 |